© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 14545
    Prev
    Next
    INDEX
    Explanations

    references to music and song elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     externi
    -0.49
    __":
    -0.41
     auk
    -0.38
    ppuden
    -0.37
    ateurs
    -0.36
    ExtendWith
    -0.36
    itive
    -0.35
    Mål
    -0.35
    ]),
    
    -0.35
     orquí
    -0.35
    POSITIVE LOGITS
     song
    0.89
     songs
    0.82
    song
    0.68
     canzone
    0.67
     lyrics
    0.65
    Song
    0.64
    songs
    0.63
     canción
    0.62
     sung
    0.62
     şark
    0.60
    Activations Density 0.082%

    No Known Activations